Related papers: Exploring Disentanglement with Multilingual and Mo…
The primary characteristic of robust speaker representations is that they are invariant to factors of variability not related to speaker identity. Disentanglement of speaker representations is one of the techniques used to improve…
Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning. However, the existing VAE models have some…
Analyses of self-supervised speech models have begun to reveal where and how they represent different types of information. However, almost all analyses have focused on English. Here, we examine how wav2vec2 models trained on four different…
In this paper, we propose a novel model called Learnable VAE (L-VAE), which learns a disentangled representation together with the hyperparameters of the cost function. L-VAE can be considered as an extension of \b{eta}-VAE, wherein the…
Expressive voice conversion performs identity conversion for emotional speakers by jointly converting speaker identity and emotional style. Due to the hierarchical structure of speech emotion, it is challenging to disentangle the emotional…
End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…
Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this…
The careful construction of audio representations has become a dominant feature in the design of approaches to many speech tasks. Increasingly, such approaches have emphasized "disentanglement", where a representation contains only parts of…
Semi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning.…
This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives, for label…
Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…
Learning disentangled causal representations is a challenging problem that has gained significant attention recently due to its implications for extracting meaningful information for downstream tasks. In this work, we define a new notion of…
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector…
Self-supervised representations of speech are currently being widely used for a large number of applications. Recently, some efforts have been made in trying to analyze the type of information present in each of these representations. Most…
We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captures per-utterance…
This paper proposes an interesting voice and accent joint conversion approach, which can convert an arbitrary source speaker's voice to a target speaker with non-native accent. This problem is challenging as each target speaker only has…
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and…
Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…
There has been an increasing research interest in cross-age speaker verification~(CASV). However, existing speaker verification systems perform poorly in CASV due to the great individual differences in voice caused by aging. In this paper,…
Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that…